Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and coordinate values in numeric or tabular formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    coordinates and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſch
    -0.64
     fubject
    -0.63
     Reſ
    -0.58
     ſche
    -0.57
    ReusableCell
    -0.56
     Chrift
    -0.54
     itſelf
    -0.54
     ſtand
    -0.54
     Anſ
    -0.53
    craft
    -0.52
    POSITIVE LOGITS
    GOTREF
    0.51
     незавершена
    0.43
     coordenadas
    0.41
    ToProps
    0.38
    WriteBarrier
    0.38
     fazenda
    0.38
     NSCoder
    0.37
    WebServlet
    0.37
    retudo
    0.37
     paisagem
    0.36
    Act Density 0.001%

    No Known Activations